Pretrained model on programming language python using the t5 large model architecture. It was first released in this repository. This model is trained on tokenized python code functions: it works best with tokenized python functions.
This CodeTrans model is based on the
t5-large model. It has its own SentencePiece vocabulary model. It used transfer-learning pre-training on 7 unsupervised datasets in the software development domain. It is then fine-tuned on the code documentation generation task for the python function/method.
The model could be used to generate the description for the python function or be fine-tuned on other python code tasks. It can be used on unparsed and untokenized python code. However, if the python code is tokenized, the performance should be better.
Here is how to use this model to generate python function documentation using Transformers SummarizationPipeline:
from transformers import AutoTokenizer, AutoModelWithLMHead, SummarizationPipeline pipeline = SummarizationPipeline( model=AutoModelWithLMHead.from_pretrained("SEBIS/code_trans_t5_large_code_documentation_generation_python_transfer_learning_finetune"), tokenizer=AutoTokenizer.from_pretrained("SEBIS/code_trans_t5_large_code_documentation_generation_python_transfer_learning_finetune", skip_special_tokens=True), device=0 ) tokenized_code = "def e ( message , exit_code = None ) : print_log ( message , YELLOW , BOLD ) if exit_code is not None : sys . exit ( exit_code )" pipeline([tokenized_code])
Run this example in colab notebook.
The supervised training tasks datasets can be downloaded on Link
The model was trained on a single TPU Pod V3-8 for 240,000 steps in total, using sequence length 512 (batch size 4096). It has a total of approximately 220M parameters and was trained using the encoder-decoder architecture. The optimizer used is AdaFactor with inverse square root learning rate schedule for pre-training.
This model was then fine-tuned on a single TPU Pod V2-8 for 500 steps in total, using sequence length 512 (batch size 256), using only the dataset only containing python code.
For the code documentation tasks, different models achieves the following results on different programming languages (in BLEU score):
Test results :
|State of the art||19.06||17.65||18.07||25.16||12.16||14.90|
Select AutoNLP in the “Train” menu to fine-tune this model automatically.
- Downloads last month